© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36289
    Prev
    Next
    INDEX
    Explanations

    discussions related to political debates and policy arguments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    0.9%
    681
    +0.14
    0.5%
    546
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    681
    +0.24
    0.11
    146
    +0.14
    0.10
    136
    +0.14
    0.12
    Negative Logits
    Ô
    -0.94
    bors
    -0.94
    âĸĪâĸĪ
    -0.93
    zona
    -0.91
     Okin
    -0.86
     CLSID
    -0.85
     Tsarnaev
    -0.84
    ASED
    -0.83
    atl
    -0.82
     âĸĪ
    -0.81
    POSITIVE LOGITS
     MPs
    1.25
     favourites
    1.12
     favourite
    1.10
     Tories
    1.07
     councillors
    1.06
     councillor
    1.05
     colours
    1.03
     Ministers
    0.98
     whip
    0.98
     centre
    0.98
    Activations Density 14.055%

    No Known Activations